An Adaptive Sampling Algorithm for Solving Markov Decision Processes
From MaRDI portal
Publication:5322077
DOI10.1287/opre.1040.0145zbMath1165.90672OpenAlexW2016647253WikidataQ57382677 ScholiaQ57382677MaRDI QIDQ5322077
Jiaqiao Hu, Steven I. Marcus, Michael C. Fu, Hyeong Soo Chang
Publication date: 17 July 2009
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: http://hdl.handle.net/1903/6264
Related Items
Decomposition and Adaptive Sampling for Data-Driven Inverse Linear Optimization, Nonasymptotic Analysis of Monte Carlo Tree Search, Dynamic Pricing and Learning with Finite Inventories, Adaptive aggregation for reinforcement learning in average reward Markov decision processes, A variable neighborhood search based algorithm for finite-horizon Markov decision processes, Approximate stochastic annealing for online control of infinite horizon Markov decision processes, Reinforcement Learning, Bit by Bit, Online Sequential Optimization with Biased Gradients: Theory and Applications to Censored Demand, Sensitivity-based nested partitions for solving finite-horizon Markov decision processes, Nonstationary Bandits with Habituation and Recovery Dynamics, Optimistic Monte Carlo Tree Search with Sampled Information Relaxation Dual Bounds, Sampled fictitious play for approximate dynamic programming, Multi-armed bandits based on a variant of simulated annealing, From reinforcement learning to optimal control: a unified framework for sequential decisions, Multi-agent reinforcement learning: a selective overview of theories and algorithms